CoEvolvable hardware platform for automatic hardware design of neural networks

This paper proposes a system for the automatic hardware design of neural networks based on cooperative co evolutionary paradigms and multiple reconfigurable devices. Our system is composed of logic synthesis tool, multiple reconfigurable devices and an embedded processor executing the co evolutionary algorithm. The partitioning of the engineering design process follows current practices in hardware/software co design based on both information on arrival rate λ of requests and the service time μ of the reconfigurable Devices. The system is suitable under some conditions for industrial applications as a reactive system but also because it can be connected to multiple systems in a totally networked industrial environment which allows download of the same hardware configuration on multiple on line devices.